Dually Interactive Matching Network for Personalized Response Selection in Retrieval-Based Chatbots

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 1845–1854, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 1845 Dually Interactive Matching Network for Personalized Response Selection in Retrieval-Based Chatbots Jia-Chen Gu1, Zhen-Hua Ling1, Xiaodan Zhu2, Quan Liu1,3 1National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China 2ECE, Queen’s University, Kingston, Canada 3State Key Laboratory of Cognitive Intelligence, iFLYTEK Research, Hefei, China gujc@mail.ustc.edu.cn, zhling@ustc.edu.cn, xiaodan.zhu@queensu.ca, quanliu@ustc.edu.cn Abstract This paper proposes a dually interactive matching network (DIM) for presenting the personalities of dialogue agents in retrieval- based chatbots. This model develops from the interactive matching network (IMN) which models the matching degree between a context composed of multiple utterances and a response candidate. Compared with previous persona fusion approaches which enhance the representation of a context by calculating its similarity with a given persona, the DIM model adopts a dual matching architecture, which performs interactive matching between responses and contexts and between responses and personas respectively for ranking response candidates. Experimental results on PERSONA-CHAT dataset show that the DIM model outperforms its baseline model, i.e., IMN with persona fusion, by a margin of 14.5% and outperforms the current state-of-the-art model by a margin of 27.7% in terms of top-1 accuracy hits@1. 1 Introduction Building a conversation system with intelligence is challenging. Response selection, which aims to select a potential response from a set of candidates given the context of a conversation, is an important technique to build retrieval-based chatbots (Zhou et al., 2018). Many previous studies on single- turn (Wang et al., 2013) or multi-turn response selection (Lowe et al., 2015; Zhou et al., 2018; Gu et al., 2019) rank response candidates according to their semantic relevance with the given context. With the emergence and popular use of personal assistants such as Apple Siri, Google Now and Microsoft Cortana, the techniques of making per- sonalized dialogues has attracted much research attention in recent years (Li et al., 2016; Zhang et al., 2018; Mazar´e et al., 2018). Zhang et al. (2018) constructed a PERSONA-CHAT dataset for building personalized dialogue agents, where each persona was represented as multiple sen- tences of profile description. An example dialogue conditioned on given profiles from this dataset is given in Table 1 for illustration. A persona fusion method for personalized re- sponse selection was also proposed by Zhang et al. (2018). In this method, given a context and a persona composed of several profile sentences, the similarities between the context representa- tion and all profile sentences are computed first using attention to get the persona representation. Then, the persona representation is applied to enhance the context representation by a simple concatenation or addition operation. Finally, the enhanced context representation is used to rank response candidates. This method has two main deficiencies. First, the context is treated as a whole for calculating its attention towards profile sentences. However, each context is composed …

Content truncated to 500 words